IEICE TRANSACTIONS on Information
Multi-Scale Multi-Level Generative Model in Scene Classification
Summary :
Previous works show that the probabilistic Latent Semantic Analysis (pLSA) model is one of the best generative models for scene categorization and can obtain an acceptable classification accuracy. However, this method uses a certain number of topics to construct the final image representation. In such a way, it restricts the image description to one level of visual detail and cannot generate a higher accuracy rate. In order to solve this problem, we propose a novel generative model, which is referred to as multi-scale multi-level probabilistic Latent Semantic Analysis model (msml-pLSA). This method consists of two parts: multi-scale part, which extracts visual details from the image of diverse resolutions, and multi-level part, which concentrates multiple levels of topic representation to model scene. The msml-pLSA model allows for the description of fine and coarse local image detail in one framework. The proposed method is evaluated on the well-known scene classification dataset with 15 scene categories, and experimental results show that the proposed msml-pLSA model can improve the classification accuracy compared with the typical classification methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E94-D No.1 pp.167-170
- Publication Date
- 2011/01/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E94.D.167
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Wenjie XIE, De XU, Yingjun TANG, Geng CUI, "Multi-Scale Multi-Level Generative Model in Scene Classification" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 1, pp. 167-170, January 2011, doi: 10.1587/transinf.E94.D.167.
Abstract: Previous works show that the probabilistic Latent Semantic Analysis (pLSA) model is one of the best generative models for scene categorization and can obtain an acceptable classification accuracy. However, this method uses a certain number of topics to construct the final image representation. In such a way, it restricts the image description to one level of visual detail and cannot generate a higher accuracy rate. In order to solve this problem, we propose a novel generative model, which is referred to as multi-scale multi-level probabilistic Latent Semantic Analysis model (msml-pLSA). This method consists of two parts: multi-scale part, which extracts visual details from the image of diverse resolutions, and multi-level part, which concentrates multiple levels of topic representation to model scene. The msml-pLSA model allows for the description of fine and coarse local image detail in one framework. The proposed method is evaluated on the well-known scene classification dataset with 15 scene categories, and experimental results show that the proposed msml-pLSA model can improve the classification accuracy compared with the typical classification methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.167/_p
Copy
@ARTICLE{e94-d_1_167,
author={Wenjie XIE, De XU, Yingjun TANG, Geng CUI, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Scale Multi-Level Generative Model in Scene Classification},
year={2011},
volume={E94-D},
number={1},
pages={167-170},
abstract={Previous works show that the probabilistic Latent Semantic Analysis (pLSA) model is one of the best generative models for scene categorization and can obtain an acceptable classification accuracy. However, this method uses a certain number of topics to construct the final image representation. In such a way, it restricts the image description to one level of visual detail and cannot generate a higher accuracy rate. In order to solve this problem, we propose a novel generative model, which is referred to as multi-scale multi-level probabilistic Latent Semantic Analysis model (msml-pLSA). This method consists of two parts: multi-scale part, which extracts visual details from the image of diverse resolutions, and multi-level part, which concentrates multiple levels of topic representation to model scene. The msml-pLSA model allows for the description of fine and coarse local image detail in one framework. The proposed method is evaluated on the well-known scene classification dataset with 15 scene categories, and experimental results show that the proposed msml-pLSA model can improve the classification accuracy compared with the typical classification methods.},
keywords={},
doi={10.1587/transinf.E94.D.167},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Multi-Scale Multi-Level Generative Model in Scene Classification
T2 - IEICE TRANSACTIONS on Information
SP - 167
EP - 170
AU - Wenjie XIE
AU - De XU
AU - Yingjun TANG
AU - Geng CUI
PY - 2011
DO - 10.1587/transinf.E94.D.167
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2011
AB - Previous works show that the probabilistic Latent Semantic Analysis (pLSA) model is one of the best generative models for scene categorization and can obtain an acceptable classification accuracy. However, this method uses a certain number of topics to construct the final image representation. In such a way, it restricts the image description to one level of visual detail and cannot generate a higher accuracy rate. In order to solve this problem, we propose a novel generative model, which is referred to as multi-scale multi-level probabilistic Latent Semantic Analysis model (msml-pLSA). This method consists of two parts: multi-scale part, which extracts visual details from the image of diverse resolutions, and multi-level part, which concentrates multiple levels of topic representation to model scene. The msml-pLSA model allows for the description of fine and coarse local image detail in one framework. The proposed method is evaluated on the well-known scene classification dataset with 15 scene categories, and experimental results show that the proposed msml-pLSA model can improve the classification accuracy compared with the typical classification methods.
ER -
English
